Pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CL 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

SGPO: Self-Generated Preference Optimization based on Self-Improver

cs.CL · 2025-07-27 · conditional · novelty 6.0

SGPO uses one shared model to refine its own responses and then optimize with DPO on those self-generated preference pairs, outperforming DPO and SPIN on AlpacaEval 2.0 and Arena-Hard without external preference labels.

citing papers explorer

Showing 1 of 1 citing paper.

  • SGPO: Self-Generated Preference Optimization based on Self-Improver cs.CL · 2025-07-27 · conditional · none · ref 3

    SGPO uses one shared model to refine its own responses and then optimize with DPO on those self-generated preference pairs, outperforming DPO and SPIN on AlpacaEval 2.0 and Arena-Hard without external preference labels.